Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prist
    0.32
    Notably
    0.32
     luis
    0.31
     (“
    0.31
    大家
    0.31
     ("
    0.30
     potencialmente
    0.30
    www
    0.30
    （
    0.30
    જે
    0.30
    POSITIVE LOGITS
     other
    0.52
     другие
    0.52
     andere
    0.51
     autres
    0.49
     других
    0.49
    その他の
    0.49
     другими
    0.49
     अन्य
    0.46
     lainnya
    0.45
     ఇతర
    0.45
    Act Density 0.249%

    No Known Activations